Event ·Official first-hand

DeepSeek-V4 长上下文服务系统 RedKnot-MLA 发布

DeepSeek-V4 推出 RedKnot-MLA 系统,采用多头部离线-在线重用技术。该系统在 256K 上下文长度下,F1 分数提升 3.24 个百分点,EM 分数提升 4.16 个百分点。DeepSeek-V4-Flash 使用 37 个可重用层,达到 75.29% 的逻辑头部行上限,Pro-0813 配置达到 78.89%。

Current read

DeepSeek 推出了 RedKnot-MLA 系统,能显著提升长上下文服务的速度和效率,在多个基准测试中表现优异。

4 sources73° AI heatLast updated 2026/9/7 03:59:33

Evidence

4 sources
Primary sourcearXiv: DeepSeek
View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.